Pinned Loading

1. vllm-project/vllm vllm-project/vllm Public

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python 32.7k 5k

2. AutoAWQ AutoAWQ Public

   Forked from casper-hansen/AutoAWQ

   AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

   Python

3. AutoFP8 AutoFP8 Public

   Forked from neuralmagic/AutoFP8

   Python

4. llm-compressor llm-compressor Public

   Forked from vllm-project/llm-compressor

   Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

   Python